Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 68 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.5106. Min Act: -0.1700
Data Index: 7044347 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.4794. Min Act: -0.1700
Data Index: 450832 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2606. Min Act: -0.1700
Data Index: 5201239 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2606. Min Act: -0.1700
Data Index: 217870 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2606. Min Act: -0.1700
Data Index: 908957 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.2294. Min Act: -0.1700
Data Index: 8011332 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1981. Min Act: -0.1700
Data Index: 8529058 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1669. Min Act: -0.1700
Data Index: 1188001 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 5264702 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 4625293 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 2360851 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1356. Min Act: -0.1700
Data Index: 3899970 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 3355252 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.1044. Min Act: -0.1700
Data Index: 5058151 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 3906777 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0731. Min Act: -0.1700
Data Index: 6373359 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0419. Min Act: -0.1700
Data Index: 2741294 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0419. Min Act: -0.1700
Data Index: 8615020 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 3037888 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5106. Min Range: -5.5106
Max Act: 5.0106. Min Act: -0.1700
Data Index: 7641677 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19